added custom handler

README.md

@@ -1,3 +1,99 @@
 ---
 license: openrail++
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-guided-to-image-inpainting
+- endpoints-template
 ---
+
+# Fork of [stabilityai/stable-diffusion-2-inpainting](https://huggingface.co/stabilityai/stable-diffusion-2-inpainting)
+
+> Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input.
+> For more information about how Stable Diffusion functions, please have a look at [🤗's Stable Diffusion with 🧨Diffusers blog](https://huggingface.co/blog/stable_diffusion).
+
+For more information about the model, license and limitations check the original model card at [stabilityai/stable-diffusion-2-inpainting](https://huggingface.co/stabilityai/stable-diffusion-2-inpainting).
+
+---
+
+This repository implements a custom `handler` task for `text-guided-to-image-inpainting` for 🤗 Inference Endpoints. The code for the customized pipeline is in the [pipeline.py](https://huggingface.co/philschmid/stable-diffusion-2-inpainting-endpoint/blob/main/handler.py).
+
+There is also a [notebook](https://huggingface.co/philschmid/stable-diffusion-2-inpainting-endpoint/blob/main/create_handler.ipynb) included, on how to create the `handler.py`
+
+**How it works:**
+`image`          | `mask_image`
+:-------------------------:|:-------------------------:|
+<img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" alt="drawing" width="300"/> | <img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" alt="drawing" width="300"/>
+
+
+`prompt`          | `Output`
+:-------------------------:|:-------------------------:|
+<span style="position: relative;bottom: 150px;">Face of a bengal cat, high resolution, sitting on a park bench</span> | <img src="./result.png" alt="drawing" width="300"/>
+
+
+### expected Request payload
+
+```json
+{
+    "inputs": "A prompt used for image generation",
+    "image" : "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAABGdBTUEAALGPC",
+    "mask_image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAABGdBTUEAALGPC",
+}
+```
+
+below is an example on how to run a request using Python and `requests`.
+
+## Run Request 
+```python
+import json
+from typing import List
+import requests as r
+import base64
+from PIL import Image
+from io import BytesIO
+
+ENDPOINT_URL = ""
+HF_TOKEN = ""
+
+import base64
+from PIL import Image
+from io import BytesIO
+
+# helper image utils
+def encode_image(image_path):
+  with open(image_path, "rb") as i:
+    b64 = base64.b64encode(i.read())
+  return b64.decode("utf-8")
+
+prompt = "Face of a bengal cat, high resolution, sitting on a park bench"
+
+# test the handler
+pred = my_handler(request)
+
+
+def predict(prompt, image, mask_image):
+    image = encode_image(image)
+    mask_image = encode_image(mask_image)
+
+    # prepare sample payload
+    request = {"inputs": prompt, "image": image, "mask_image": mask_image}
+    # headers
+    headers = {
+        "Authorization": f"Bearer {HF_TOKEN}",
+        "Content-Type": "application/json",
+        "Accept": "image/png" # important to get an image back
+    }
+
+    response = r.post(ENDPOINT_URL, headers=headers, json=payload)
+    img = Image.open(BytesIO(response.content))
+    return img
+
+prediction = predict(
+    prompt="Face of a bengal cat, high resolution, sitting on a park bench",
+    image="dog.png",
+    mask_image="mask_dog.png"
+)
+```
+expected output
+
+![sample](result.png)

handler.py

@@ -66,4 +66,4 @@ class EndpointHandler():
         base64_image = base64.b64decode(image_string)
         buffer = BytesIO(base64_image)
         image = Image.open(buffer)
-        return image.convert("RGB").thumbnail((768, 768))
+        return image